Imperial College London Seeks AI Safety Postdoc to Probe Hidden Dangers of Frontier Models

Imperial College London researcher oanacamb has announced a funded opening for a postdoc in AI Safety & Alignment, focused on detecting unstated dangerous capabilities in frontier AI models.

2026-10-24 ~ 2026-10-24 · 2 related posts

• Imperial College London opens postdoc position on detecting dangerous frontier-model capabilities — oanacamb · 2026-10-24

1 near-duplicate retellings: oanacamb